--- title: "Mongolia — research institutions, scientists and papers" description: "Mongolia: 1 institutions with papers in our library in 1 agglomerations, 1 people with a page, 2 works, 127 citations." canonical: "https://research.elamur.ai/free/en/countries/mongolia/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/countries/mongolia/) [home](https://md.research.elamur.ai/free/en/) / [countries](https://md.research.elamur.ai/free/en/countries/) / Mongolia # Mongolia Country 1 institution in 1 agglomeration · [all countries](https://md.research.elamur.ai/free/en/countries/) [**1** institution with a page](https://md.research.elamur.ai/free/en/countries/mongolia/#institutions) · [**1** agglomeration](https://md.research.elamur.ai/free/en/countries/mongolia/#agglomerations) · [**1** person with a page](https://md.research.elamur.ai/free/en/countries/mongolia/#authors) · [**2** works in our library](https://md.research.elamur.ai/free/en/countries/mongolia/#works) · [**127** citations of their works](https://md.research.elamur.ai/free/en/countries/mongolia/#works) ## About ### Profile Mongolia is represented on this site by a compact but focused body of research. Its work here comes from a single institution, the [National University of Mongolia](https://md.research.elamur.ai/free/en/universities/national-university-of-mongolia/), a university in the capital region of [Ulaanbaatar](https://md.research.elamur.ai/free/en/agglomerations/ulaanbaatar/). Ulaanbaatar is also the only city region of the country with works in the library, so the country's profile here and the profile of its capital coincide almost entirely. The [institutions](https://md.research.elamur.ai/free/en/countries/mongolia/institutions/) and [agglomerations](https://md.research.elamur.ai/free/en/countries/mongolia/agglomerations/) overviews for the country each lead back to this one university and this one city. The research credited to Mongolia sits in a single field, [linguistics and languages](https://md.research.elamur.ai/free/en/shelves/linguistics/). Within that field it concentrates on [morphology](https://md.research.elamur.ai/free/en/topics/morphology/), the study of how words are built from smaller meaningful parts, and it also touches on [multilingual and cross-lingual natural language processing](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/). The works here are computational. They do not describe the structure of one language in detail. Instead they build resources and evaluation settings that let software analyse word structure across many languages at once. Mongolia can also be compared with other nations through the site's list of [all countries](https://md.research.elamur.ai/free/en/countries/). Seen against that wider picture, its presence is narrow but clearly defined. It consists of a small group of linguistics papers whose authors include a researcher at the National University of Mongolia, together with collaborators who appear alongside them. ### History On this site, Mongolia's research begins in 2021. Its first work, the MorphyNet database, appeared that year and set out the morphological interests that run through everything the country has here. In 2022 a second work followed: the report on a shared task in morpheme segmentation, organised within the SIGMORPHON community. That task continued the same line of work and turned it from building a resource into evaluating systems. The sequence is short, but it holds together. The earlier work collected morphological relations between words on a large scale and in many languages. The later work asked researchers to build systems that could break words into their component morphemes, the very kind of structure such a resource describes. The history of Mongolia's research on this site is therefore one continuous thread in computational morphology, carried forward by the same lead author and a largely shared group of co-authors. No earlier works from the country appear in the library, and no other fields of research appear alongside this one. ### Research profile All of Mongolia's research here concerns morphology, approached through multilingual language technology. The works fall into two complementary types: a lexical resource and a community benchmark. The resource is [MorphyNet](https://md.research.elamur.ai/free/en/papers/batsuren-2021-morphynet/), a database covering both derivational and inflectional morphology in many languages. Derivation covers how new words are formed from existing ones, for example by adding a prefix or suffix that changes the meaning or the word class. Inflection covers how a word changes form to mark grammatical features such as number or tense. The database was assembled from Wiktionary, the collaboratively edited dictionary, and pulls together morphological information scattered across its entries into a single structured collection. Its reported precision is very high, which points to the authors' concern with the reliability of automatically extracted linguistic knowledge. This work belongs to both of the country's topics on this site, morphology and multilingual NLP, since its coverage reaches across many languages and is not limited to one. The benchmark is the [SIGMORPHON 2022 shared task on morpheme segmentation](https://md.research.elamur.ai/free/en/papers/batsuren-2022-morpheme-segmentation/). In a shared task, organisers set a common problem, supply data and an evaluation method, and invite teams to submit systems that are then compared on equal terms. Here the problem was to split words into their morphemes, and it covered several word-formation processes, among them compounding and derivation. The best systems reported in the task reached very high F1 scores, showing how far automatic segmentation had advanced on the data provided. The work sits under morphology on this site, and it shows the field's habit of driving progress through common evaluations. Taken together, these works show a research profile built on infrastructure for language technology rather than on single applications. The aim is to supply resources and tests that other researchers can build on. The citations these works have collected among other papers in our library suggest that this aim has been met: both are drawn on by later work in the library. ### Leading scientists The first person shown for Mongolia is [Khuyagbaatar Batsuren](https://md.research.elamur.ai/free/en/authors/khuyagbaatar-batsuren/), affiliated with the National University of Mongolia. Batsuren is the first author of both works credited to the country. These works cover the building of the MorphyNet database and the organisation and reporting of the 2022 SIGMORPHON segmentation task. Batsuren's own profile on this site includes further papers beyond those credited to Mongolia, so the country's share is part of a wider body of work by the same author. The common thread across this work is computational morphology at multilingual scale: gathering structured knowledge about how words are formed and setting up the means to test systems that analyse that structure. [Gabor Bella](https://md.research.elamur.ai/free/en/authors/gabor-bella/) also appears among the people associated with the National University of Mongolia on this site. Bella is a co-author of both works, MorphyNet and the shared-task report, and so shares in both the resource-building and the evaluation sides of this research. The steady pairing of Batsuren and Bella across the works is the clearest sign of an ongoing working partnership behind Mongolia's presence here. ### Landmark works The most cited of Mongolia's works in our library is [The SIGMORPHON 2022 Shared Task on Morpheme Segmentation](https://md.research.elamur.ai/free/en/papers/batsuren-2022-morpheme-segmentation/), by Khuyagbaatar Batsuren, Gabor Bella and Aryaman Arora, published in 2022. The paper describes a shared task in which participating systems split words into their smallest meaningful units. It covers a range of morphological phenomena, including compounds and derived words, and reports on how the submitted systems performed. Its reference list is extensive, which reflects its role as a summary of the problem and of earlier approaches. Many papers in the library cite it, making it the country's most visible contribution here. The second landmark is [MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology](https://md.research.elamur.ai/free/en/papers/batsuren-2021-morphynet/), by Khuyagbaatar Batsuren, Gabor Bella and Fausto Giunchiglia, published in 2021. It presents a multilingual morphological database built from Wiktionary that combines derivational and inflectional relations in one resource. The authors report very high precision for the extracted material. The work is also widely cited among papers in our library, and since the later shared task deals with the same kind of word structure, MorphyNet can be read as groundwork for it. These works mark the main stages of Mongolia's research here. MorphyNet built the knowledge base, and the shared task turned that interest into an open evaluation for the wider research community. ### Labs and units The only institution through which Mongolia appears on this site is the National University of Mongolia, a university based in Ulaanbaatar. No separate departments, laboratories or research units are shown for it. Its research identity here is defined by its topics, morphology and multilingual NLP, and by the people associated with it, Khuyagbaatar Batsuren and Gabor Bella. ### Collaborations Mongolia's works in our library are collaborative. Batsuren and Bella appear together on both papers, and each paper adds a further co-author. On the shared-task report the third author is Aryaman Arora. On the MorphyNet paper it is Fausto Giunchiglia. The library does not show these co-authors as linked to Mongolian institutions, so the country's research here involves partners whose affiliations lie outside the National University of Mongolia's profile on this site. The SIGMORPHON shared task is itself a form of collaboration at community scale. Shared tasks bring independent teams together around common data and a common evaluation, and the task's report describes and compares the systems those teams submitted. Through this format, research credited to Mongolia connects with a broad international group working on computational morphology, even though the site does not list these participants one by one. Within Mongolia, the site shows no links between universities and companies, and no second institution with which the National University of Mongolia might work. Collaboration here runs through authorship and research communities rather than through partnerships between local institutions. ### Timeline In 2021, Mongolia's research on this site begins with MorphyNet, a large multilingual database of derivational and inflectional morphology built from Wiktionary. Khuyagbaatar Batsuren, Gabor Bella and Fausto Giunchiglia are its authors, and it establishes morphology and multilingual NLP as the country's research topics here. In 2022, the same line of research moves from resource-building to evaluation with the SIGMORPHON shared task on morpheme segmentation. Batsuren, Bella and Aryaman Arora author the report. It becomes the most cited of the country's works in our library and confirms linguistics as Mongolia's field in the library, centred on the National University of Mongolia in Ulaanbaatar. ## Where ## Agglomerations (1) 1. [**Ulaanbaatar**1 institution*127 citations*](https://md.research.elamur.ai/free/en/agglomerations/ulaanbaatar/) ## Institutions (1) ### 🎓 Universities (1) **[National University of Mongolia](https://md.research.elamur.ai/free/en/universities/national-university-of-mongolia/)**University · [Ulaanbaatar](https://md.research.elamur.ai/free/en/agglomerations/ulaanbaatar/), Mongolia*2 works · 127 citations* ## People (1) Authors with a page confirmed at its institutions, the most cited first. [🧑‍🔬**Khuyagbaatar Batsuren** National University of Mongolia 3 papers here · 335 citations](https://md.research.elamur.ai/free/en/authors/khuyagbaatar-batsuren/) ## Works in our library (2) Works of its institutions, the most cited first. 1. [**The SIGMORPHON 2022 Shared Task on Morpheme Segmentation**Khuyagbaatar Batsuren, Gabor Bella, Aryaman Arora*2022 · 71 citations*](https://md.research.elamur.ai/free/en/papers/batsuren-2022-morpheme-segmentation/) 2. [**MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology**Khuyagbaatar Batsuren, Gabor Bella, Fausto Giunchiglia*2021 · 56 citations*](https://md.research.elamur.ai/free/en/papers/batsuren-2021-morphynet/) ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 📚 Shelves 2[English · 2 works · 8.0](https://md.research.elamur.ai/free/en/shelves/en/) · [Linguistics & languages · 2 works · 8.0](https://md.research.elamur.ai/free/en/shelves/linguistics/) 🧭 Topics 2[Morphology · 2 works · 12.2](https://md.research.elamur.ai/free/en/topics/morphology/) · [Multilingual & cross-lingual NLP · 1 work · 3.7](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) ## Works by year ### 2020s [**2022** 1 work](https://md.research.elamur.ai/free/en/papers/batsuren-2022-morpheme-segmentation/) · [**2021** 1 work](https://md.research.elamur.ai/free/en/papers/batsuren-2021-morphynet/) - [← back to](https://md.research.elamur.ai/free/en/countries/) — countries